MRGAgents: A Multi-Agent Framework for Improved Medical Report Generation with Med-LVLMs
This addresses a critical issue in medical imaging for clinicians by enhancing diagnostic accuracy through more balanced and comprehensive reports, though it is incremental as it builds on existing Med-LVLM approaches.
The paper tackled the problem of medical report generation by Med-LVLMs, which often bias toward normal findings and miss critical abnormalities, by proposing MRGAgents, a multi-agent framework that fine-tunes specialized agents for different disease categories, resulting in improved report comprehensiveness and diagnostic utility over state-of-the-art methods.
Medical Large Vision-Language Models (Med-LVLMs) have been widely adopted for medical report generation. Despite Med-LVLMs producing state-of-the-art performance, they exhibit a bias toward predicting all findings as normal, leading to reports that overlook critical abnormalities. Furthermore, these models often fail to provide comprehensive descriptions of radiologically relevant regions necessary for accurate diagnosis. To address these challenges, we proposeMedical Report Generation Agents (MRGAgents), a novel multi-agent framework that fine-tunes specialized agents for different disease categories. By curating subsets of the IU X-ray and MIMIC-CXR datasets to train disease-specific agents, MRGAgents generates reports that more effectively balance normal and abnormal findings while ensuring a comprehensive description of clinically relevant regions. Our experiments demonstrate that MRGAgents outperformed the state-of-the-art, improving both report comprehensiveness and diagnostic utility.